Tree-based iterated local search for Markov random fields with applications in image analysis

The maximum a posteriori assignment for general structure Markov random fields is computationally intractable. In this paper, we exploit tree-based methods to efficiently address this problem. Our novel method, named Tree-based Iterated Local Search (T-ILS), takes advantage of the tractability of tr...

Full description

Bibliographic Details
Main Authors: Tran, The Truyen, Phung, D., Venkatesh, S.
Format: Journal Article
Published: Kluwer Academic Publishers 2014
Online Access:http://hdl.handle.net/20.500.11937/39305
_version_ 1848755555229761536
author Tran, The Truyen
Phung, D.
Venkatesh, S.
author_facet Tran, The Truyen
Phung, D.
Venkatesh, S.
author_sort Tran, The Truyen
building Curtin Institutional Repository
collection Online Access
description The maximum a posteriori assignment for general structure Markov random fields is computationally intractable. In this paper, we exploit tree-based methods to efficiently address this problem. Our novel method, named Tree-based Iterated Local Search (T-ILS), takes advantage of the tractability of tree-structures embedded within MRFs to derive strong local search in an ILS framework. The method efficiently explores exponentially large neighborhoods using a limited memory without any requirement on the cost functions. We evaluate the T-ILS on a simulated Ising model and two real-world vision problems: stereo matching and image denoising. Experimental results demonstrate that our methods are competitive against state-of-the-art rivals with significant computational gain.
first_indexed 2025-11-14T08:58:10Z
format Journal Article
id curtin-20.500.11937-39305
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T08:58:10Z
publishDate 2014
publisher Kluwer Academic Publishers
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-393052018-03-29T09:07:34Z Tree-based iterated local search for Markov random fields with applications in image analysis Tran, The Truyen Phung, D. Venkatesh, S. The maximum a posteriori assignment for general structure Markov random fields is computationally intractable. In this paper, we exploit tree-based methods to efficiently address this problem. Our novel method, named Tree-based Iterated Local Search (T-ILS), takes advantage of the tractability of tree-structures embedded within MRFs to derive strong local search in an ILS framework. The method efficiently explores exponentially large neighborhoods using a limited memory without any requirement on the cost functions. We evaluate the T-ILS on a simulated Ising model and two real-world vision problems: stereo matching and image denoising. Experimental results demonstrate that our methods are competitive against state-of-the-art rivals with significant computational gain. 2014 Journal Article http://hdl.handle.net/20.500.11937/39305 10.1007/s10732-014-9270-1 Kluwer Academic Publishers restricted
spellingShingle Tran, The Truyen
Phung, D.
Venkatesh, S.
Tree-based iterated local search for Markov random fields with applications in image analysis
title Tree-based iterated local search for Markov random fields with applications in image analysis
title_full Tree-based iterated local search for Markov random fields with applications in image analysis
title_fullStr Tree-based iterated local search for Markov random fields with applications in image analysis
title_full_unstemmed Tree-based iterated local search for Markov random fields with applications in image analysis
title_short Tree-based iterated local search for Markov random fields with applications in image analysis
title_sort tree-based iterated local search for markov random fields with applications in image analysis
url http://hdl.handle.net/20.500.11937/39305